voidly
UZ · per-country backtest

Uzbekistan forecast vs reality

Every Voidly Sentinel shutdown-risk forecast for Uzbekistan, plotted against what actually happened. 56 (predicted, observed) pairs from the rolling 30-day evaluation window.

Updated every 30 min · CC BY 4.0 · Raw JSON · Current forecast →

Forecasts evaluated
56
since Apr 17
Accuracy @ 0.5
55.4%
31/56 correct
Brier score
0.538
lower is better
Observed positive rate
86%
mean predicted 35%

Forecast time series

Blue line: forecast probability. Green ✓ markers: forecast was right. Red ✗ markers: forecast was wrong. Dashed line at 0.5 is the binary decision threshold.

0.000.250.500.751.00threshold 0.50Apr 17Jun 8

Y axis: forecast probability · Faint tick: distance to observed outcome (0 or 1)

All 56 predictions (newest first)

Eval dateForecastPred ≥ 0.5?Observed?Correct?
Jun 886.9%no event
Jun 788.1%no event
Jun 695.0%shutdown
Jun 595.0%shutdown
Jun 486.8%shutdown
Jun 386.7%shutdown
Jun 295.0%shutdown
Jun 123.2%shutdown
Jun 187.0%shutdown
May 3165.3%shutdown
May 3063.6%shutdown
May 2963.7%shutdown
May 2864.7%shutdown
May 2764.4%shutdown
May 2690.4%shutdown
May 2589.4%shutdown
May 2495.0%shutdown
May 2395.0%shutdown
May 22100.0%shutdown
May 2295.0%shutdown
May 2180.0%shutdown
May 2181.4%no event
May 207.8%no event
May 196.6%shutdown
May 186.9%shutdown
May 174.5%shutdown
May 164.9%shutdown
May 154.8%shutdown
May 143.4%shutdown
May 133.0%no event
May 124.9%no event
May 112.8%no event
May 104.1%no event
May 95.0%shutdown
May 82.8%shutdown
May 73.2%shutdown
May 64.5%shutdown
May 55.7%shutdown
May 43.8%shutdown
May 35.0%shutdown
May 24.0%shutdown
May 13.2%shutdown
Apr 304.8%shutdown
Apr 292.4%shutdown
Apr 285.1%shutdown
Apr 273.7%shutdown
Apr 264.3%shutdown
Apr 253.4%shutdown
Apr 243.3%shutdown
Apr 233.9%shutdown
Apr 225.3%shutdown
Apr 214.5%shutdown
Apr 202.9%shutdown
Apr 195.2%shutdown
Apr 183.7%shutdown
Apr 174.1%shutdown

How to read this

  • Each row is one historical forecast. We made the prediction at eval_date, then waited the 7-day horizon, then graded against the observed outcome.
  • Forecast % is the calibrated probability we published that day. Post-recalibration (2026-05-20) these now match actual observed rates much better — see the refit finding.
  • Pred ≥ 0.5 shows the binary alert decision. Note we usually fire alerts at a lower threshold (see /v1/sentinel/global_heatmap for the live cutoff) — the 0.5 column here is for backtest scoring consistency with the global confusion matrix.
  • Correct = both (pred ≥ 0.5) and (observed) agree.

Related